Learning multispectral texture features for cervical cancer detection

Yanxi Liu; Tong Zhao; Jiayong Zhang

doi:10.1109/ISBI.2002.1029220

Learning multispectral texture features for cervical cancer detection

Yanxi Liu, Tong Zhao, Jiayong Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Scopus citations

Abstract

We present a bottom-up approach for automatic cancer cell detection in multispectral microscopic thin Pap smear images. Around 4, 000 multispectral texture features are explored for cancer cell detection. Using two feature screening measures, the initial feature set is effectively reduced to a computationally manageable size. Based on pixel-level screening results, cancerous regions can thus be detected through a relatively simple procedure. Our experiments have demonstrated the potential of both multispectral and texture information to serve as valuable complementary cues to traditional detection methods.

Original language	English (US)
Title of host publication	2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings
Publisher	IEEE Computer Society
Pages	169-172
Number of pages	4
ISBN (Electronic)	078037584X
DOIs	https://doi.org/10.1109/ISBI.2002.1029220
State	Published - 2002
Event	IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Washington, United States Duration: Jul 7 2002 → Jul 10 2002

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2002-January
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Other

Other	IEEE International Symposium on Biomedical Imaging, ISBI 2002
Country/Territory	United States
City	Washington
Period	7/7/02 → 7/10/02

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Radiology Nuclear Medicine and imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISBI.2002.1029220

Cite this

Liu, Y., Zhao, T., & Zhang, J. (2002). Learning multispectral texture features for cervical cancer detection. In 2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings (pp. 169-172). Article 1029220 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2002-January). IEEE Computer Society. https://doi.org/10.1109/ISBI.2002.1029220

@inproceedings{540627b7e0004903905e03c46cb08472,

title = "Learning multispectral texture features for cervical cancer detection",

abstract = "We present a bottom-up approach for automatic cancer cell detection in multispectral microscopic thin Pap smear images. Around 4, 000 multispectral texture features are explored for cancer cell detection. Using two feature screening measures, the initial feature set is effectively reduced to a computationally manageable size. Based on pixel-level screening results, cancerous regions can thus be detected through a relatively simple procedure. Our experiments have demonstrated the potential of both multispectral and texture information to serve as valuable complementary cues to traditional detection methods.",

author = "Yanxi Liu and Tong Zhao and Jiayong Zhang",

note = "Publisher Copyright: {\textcopyright} 2002 IEEE.; IEEE International Symposium on Biomedical Imaging, ISBI 2002 ; Conference date: 07-07-2002 Through 10-07-2002",

year = "2002",

doi = "10.1109/ISBI.2002.1029220",

language = "English (US)",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "169--172",

booktitle = "2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings",

address = "United States",

}

Liu, Y, Zhao, T & Zhang, J 2002, Learning multispectral texture features for cervical cancer detection. in 2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings., 1029220, Proceedings - International Symposium on Biomedical Imaging, vol. 2002-January, IEEE Computer Society, pp. 169-172, IEEE International Symposium on Biomedical Imaging, ISBI 2002, Washington, United States, 7/7/02. https://doi.org/10.1109/ISBI.2002.1029220

Learning multispectral texture features for cervical cancer detection. / Liu, Yanxi; Zhao, Tong; Zhang, Jiayong.
2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings. IEEE Computer Society, 2002. p. 169-172 1029220 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2002-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Learning multispectral texture features for cervical cancer detection

AU - Liu, Yanxi

AU - Zhao, Tong

AU - Zhang, Jiayong

PY - 2002

Y1 - 2002

N2 - We present a bottom-up approach for automatic cancer cell detection in multispectral microscopic thin Pap smear images. Around 4, 000 multispectral texture features are explored for cancer cell detection. Using two feature screening measures, the initial feature set is effectively reduced to a computationally manageable size. Based on pixel-level screening results, cancerous regions can thus be detected through a relatively simple procedure. Our experiments have demonstrated the potential of both multispectral and texture information to serve as valuable complementary cues to traditional detection methods.

AB - We present a bottom-up approach for automatic cancer cell detection in multispectral microscopic thin Pap smear images. Around 4, 000 multispectral texture features are explored for cancer cell detection. Using two feature screening measures, the initial feature set is effectively reduced to a computationally manageable size. Based on pixel-level screening results, cancerous regions can thus be detected through a relatively simple procedure. Our experiments have demonstrated the potential of both multispectral and texture information to serve as valuable complementary cues to traditional detection methods.

UR - http://www.scopus.com/inward/record.url?scp=84948694517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948694517&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2002.1029220

DO - 10.1109/ISBI.2002.1029220

M3 - Conference contribution

AN - SCOPUS:84948694517

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 169

EP - 172

BT - 2002 IEEE International Symposium on Biomedical Imaging, ISBI 2002 - Proceedings

PB - IEEE Computer Society

T2 - IEEE International Symposium on Biomedical Imaging, ISBI 2002

Y2 - 7 July 2002 through 10 July 2002

ER -

Learning multispectral texture features for cervical cancer detection

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this